agentuse and agent-runtimes
These are complements: agentuse provides the execution engine for running AI agents across multiple environments, while agent-runtimes provides the protocol exposure layer to interface with those agents through different communication channels.
About agentuse
agentuse/agentuse
🤖 AI agents on autopilot. Any model. Runs local, cron, CI/CD, or Docker.
Supports Model Context Protocol (MCP) servers for tool integration with databases and APIs, uses Markdown-based agent definitions with YAML frontmatter for version control, and includes webhook triggers, cron scheduling, and sub-agent composition for complex workflows. Full execution history tracking provides debugging and token usage metrics across Claude, GPT, and open-source models.
About agent-runtimes
datalayer/agent-runtimes
🤖 🚀 Agent Runtimes - Expose AI Agents through multiple protocols.
Supports multiple agent frameworks (Pydantic AI, LangChain, Jupyter AI) through unified adapters and exposes them via protocol abstraction (ACP, Vercel AI SDK, MCP-UI, A2A) without code changes. Built on FastAPI with a tool registry for MCP and custom tools, plus React components (ChatBase, ChatSidebar, ChatFloating) for frontend integration. Includes cloud runtime management via Zustand for launching compute resources and orchestrating notebook/document editor AI assistants.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work